work
pi on your runner
Reads the issue, explores, edits, runs your commands and tests, and commits — on its own.
‹ all agents
on demand
Builder
builder
On demand only — customised and tailored for specific projects, use cases and guardrails. It reads the repo's own AGENT.md and conventions before writing anything, and makes the smallest coherent change that resolves the issue. The PR it opens is reviewed by your review and security agents like anyone else's — it does not get a pass for being a machine.
- Triggersa run on your own CI runner, when enabled for your engagement
- Modelpi on your runner, calling Cruise with your key and the lane on your Builder card
- Outputa branch and a PR — ready when your tests pass on the action's own run, a draft otherwise
- AvailabilityOn demand only — contact our team if you need it
Its pull requests are reviewed by your other agents exactly like a human's. It does not merge, and it does not get a pass for being a machine.
How a run works
verify
Your tests, re-run
The action runs your test command itself after pi finishes. pi does not grade its own work.
publish
Ready or draft
A ready pull request when the tests pass; a draft when they fail or there are none.
Sample output
The pull request it opens. Real output from a production run — not a mock-up.
fix(scan): treat a 404 from the protection endpoint as unprotected Closes #412. The check read any non-200 as "unknown", so a repository with no branch protection reported not_checked instead of a finding — the exact silent gap the epic forbids. files changed 2 (+38 −6) tests added 4 suite 186 passed grade verified-green ✓ Opened by wrokin Builder · reviewed by wrokin code-review before merge
Integration status
On demand only. Customised and tailored for specific projects, use cases and guardrails — not included in catalog plans. Contact our team if you need it. Machine surface: capabilities.json.